recap SKILL.md skillA

recap from majiayu000/spellbook is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.

Install it, pinned

mdr add majiayu000/spellbook/recap@git:20260705.3303aa9

Pins git:20260705.3303aa9 in mdr.lock. Pin the fingerprint instead.

Audit grade: A, 17 of 17 checks passed
Kind: SKILL.md skill
Repository: majiayu000/spellbook
Path: skills/recap/SKILL.md
Versions recorded: 4
Latest version: git:20260705.3303aa9, committed Jul 5, 2026
First version recorded: Jul 3, 2026
Size: 5,840 bytes
Repository stars: 289
License: MIT

回顾最近 N 天的 Claude Code 使用记录——扫描原始会话数据，按主题分组汇总"我都做了什么"，并从个人操作系统视角输出模式、风险与增删建议。当用户说 /recap、"看看我这几天做了什么"、"回顾一下我最近的会话"、"这两天我用 claude 干了啥"、"活动回顾" 时使用。.

Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.

What the file says

# Claude Recap — 近期活动回顾与操作系统审计

从原始行为数据（而非用户自述）回答三个问题：
1. 我最近都在做什么？
2. 里面有什么可复用的模式？
3. 我的工作系统该加什么、该删什么？

## 与近亲 skill 的边界（不要重复造）

- 深度认知分析（Dreyfus/Bloom 五层画像）→ 转交 `cognitive-portrait`
- 组合违规核验（冻结仓库、未推送工作）→ 转交 `better-audit`
- Codex 历史自省 → 转交 `codex-retrospective`
- 本 skill 只做：**轻量、无依赖、直接读 jsonl 的活动回顾 + 系统级建议**

## Step 1: 提取数据（确定性部分，用脚本）

脚本随本 skill 分发（`scripts/extract_sessions.py`）。Claude 安装位于 `~/.claude/skills/recap`，Codex 安装位于 `~/.agents/skills/recap`，先解析实际位置再运行：

```bash
SKILL_DIR=$(ls -d ~/.claude/skills/recap ~/.agents/skills/recap 2>/dev/null | head -1)
python3 "$SKILL_DIR/scripts/extract_sessions.py" --days 2
```

- `--days N` 调整回看窗口（默认 2；周回顾用 7）
- `--json` 输出结构化数据供进一步处理
- 输出：每个主会话的机器、项目、窗口内起止时间、用户消息数、工具调用数、子 agent 数、体积、前 3 条用户消息
- 统计只计入窗口内的消息；跨窗口 resume 的老会话会标 `resumed`，其窗口前的历史不会混入本次回顾

### 跨机器汇聚（可选）

`scripts/sync_remote_sessions.sh` 把远程机器的 `~/.claude/projects` rsync 到本机 `~/.claude/remote-sessions/<host>/projects`，extract 脚本会自动发现这些目录并一并扫描（会话标 `@<host>`）：

```bash
"$SKILL_DIR/scripts/sync_remote_sessions.sh" starlight    # 或 RECAP_SYNC_HOSTS="host1 host2"
```

- 前提：目标机器已配置 SSH 免密（`~/.ssh/config` 里的 host 别名）
- 建议挂 cron 每日同步；某台机器同步失败会返回失败状态，避免误以为数据完整
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint

mdr add majiayu000/spellbook/recap@sha256:5556f9dc070a9a3d

The line at the top of this page pins the label git:20260705.3303aa9, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.

Badge

[![mdr](https://markdownregistry.com/badge/art_qe5ryktwyxljabon.svg)](https://markdownregistry.com/a/art_qe5ryktwyxljabon)

3 badge image fetches in 30 days. What the badge shows.

Versions

The registry has recorded 4 versions of this file, between Jul 3, 2026 and Jul 5, 2026, more than one a day.

version	committed	commit	size	audit
git:20260705.3303aa9 latest	2026-07-05	3303aa9	5,840 B	A	view · diff
git:20260703.db88b0d	2026-07-03	db88b0d	5,783 B	A	view · diff
git:20260703.d6bc2ec	2026-07-03	d6bc2ec	5,155 B	A	view · diff
git:20260703.33476a4	2026-07-03	33476a4	4,746 B	A	view

Audit of the latest version

A 17 of 17 checks passed. Fixed automatic checks with no AI involved, so the same checks give the same answer every run.

pass: Frontmatter block present
pass: Frontmatter declares a name
pass: Frontmatter declares a description
pass: Size between 200 bytes and 200 KB (5840 bytes)
pass: No zero-width or bidi control characters
pass: No instruction hidden inside an HTML comment
pass: No link to an exfiltration or paste host
pass: No credential-shaped string
pass: No instruction to send local credentials anywhere
pass: No text hidden with inline styles
pass: No prompt-injection phrasing
pass: No curl or wget piped into a shell
pass: No recursive delete of root, home or parent
pass: No instruction to read or print local credentials
pass: No base64 blob over 200 characters
pass: No link to a raw IP address
pass: No script tag

Source

GitHub

majiayu000/spellbook · 289 stars · license MIT · pushed 2026-11-02 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_qe5ryktwyxljabon
GET https://markdownregistry.com/api/v1/resolve?ref=majiayu000/spellbook/recap
GET https://markdownregistry.com/api/v1/blob/5556f9dc070a9a3dad2bf62babc10867ef24135112b76d9221aa0199ec569be3

Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.

Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.

More from majiayu000/spellbook

AGENTS.md AGENTS.md file

majiayu000/spellbook · AGENTS.md

git:20260630.1f0cf93 · audit A · 289 stars

idea-analogist SKILL.md skill

majiayu000/spellbook · plugins/idea-coach/skills/idea-analogist/SKILL.md · 想法群聊室 — 类比者角色。被 idea-team 主编排器调用，或用户单独说"类比一下"、"别的行业有没有"、"yes-and 扩展"、"X 让你想到什么"、"跨界启示"时触发。**专门做跨界类比 + yes-and…